Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/closed-world safety, so the description's job is to add operational context, which it does: polling this endpoint consumes 'no new research credits' and the job must already be owned. It does not cover rate limits or what happens if the job ID is unknown or already cancelled.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, no filler, with the action and the return payload front-loaded and the anti-pattern warning placed second. Every sentence carries distinct information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description enumerates the meaningful return fields (results, source limitations, constraint coverage, terminal status), which is what an agent needs to decide when to stop polling. Polling cadence and unknown-job behavior are the only notable gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the single jobId parameter has no description, so the description must compensate. It partially does by establishing that the job must be an 'owned' job and must be an existing one rather than newly created, but gives no format or source-of-the-ID guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (poll/retrieve) and resource (an owned search job) and enumerates what comes back: results, source limitations, constraint coverage, terminal status. The sentence 'do not start another search' implicitly separates it from the search-initiating siblings such as search_leads.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Poll the existing job; do not start another search' gives an explicit when-to-use and a clear exclusion. It stops short of naming the sibling to call instead for a new search, or of saying how often to poll, so it is not fully exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.